© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128602
    Prev
    Next
    INDEX
    Explanations

    css properties and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -1.52
     it
    -1.33
     trouvait
    -1.21
     then
    -1.14
     your
    -1.10
    ślę
    -1.10
    kish
    -1.09
     obok
    -1.09
     depois
    -1.08
     from
    -1.07
    POSITIVE LOGITS
     poser
    1.29
     ภาพ
    1.19
     سایر
    1.14
     velg
    1.13
    はなく
    1.13
     venge
    1.12
     mangled
    1.09
     mutilated
    1.07
     jist
    1.06
    other
    1.05
    Activations Density 0.006%

    No Known Activations